Lightnews — Scholar-powered news

Reposted by Rui Yang

David A Knowles @davidaknowles.bsky.social · May 15

Free in-person registration is open for #MLCB2025! Sept 10-11 at @nygenome.org and online at youtube.com/@mlcbconf. Paper/abstract deadline is June 1, more deets including our fantastic invited speaker lineup at mlcb.org! Please RP.

Machine Learning in Computational Biology

Youtube channel for the Machine Learning in Computational Biology conference: https://mlcb.github.io/

youtube.com

22 42

Rui Yang @ruiyang.bsky.social · May 15

Congratulations Soumya!

3

Reposted by Rui Yang

Jacob Schreiber @jmschreiber91.bsky.social · Apr 24

Our preprint on designing and editing cis-regulatory elements using Ledidi is out! Ledidi turns *any* ML model (or set of models) into a designer of edits to DNA sequences that induce desired characteristics.

Preprint: www.biorxiv.org/content/10.1...
GitHub: github.com/jmschrei/led...

Programmatic design and editing of cis-regulatory elements

The development of modern genome editing tools has enabled researchers to make such edits with high precision but has left unsolved the problem of designing these edits. As a solution, we propose Ledi...

www.biorxiv.org

2 37 120

Reposted by Rui Yang

Jacob Schreiber @jmschreiber91.bsky.social · Mar 22

Comparing chromatin contact maps at scale: methods and insights

www.nature.com/articles/s41...

Comparing chromatin contact maps at scale: methods and insights - Nature Methods

This study presents a benchmarking study of methods for comparing chromatin contact maps in 3D genome research.

www.nature.com

7 16

Reposted by Rui Yang

Jian Zhou @zhou-jian.bsky.social · Feb 19

Excited to share our newest preprint! Glad to see how this evolved from a serendipitous finding from a rotation project. Led by the brilliant graduate student
@ycz23.bsky.social‬

Yuchen Zhang @ycz23.bsky.social · Feb 19

Excited to share our new work, “Inverse Flow and Consistency Models”! We tackle inverse generation problems—like denoising in scenarios where you only have noisy measurements and no access to clean data, which is often the case in biological data and beyond.

arxiv.org/abs/2502.11333

(1/9)

Inverse Flow and Consistency Models

Inverse generation problems, such as denoising without ground truth observations, is a critical challenge in many scientific inquiries and real-world applications. While recent advances in generative ...

arxiv.org

2 5

Reposted by Rui Yang

David A Knowles @davidaknowles.bsky.social · Jan 27

#MLCB2025 will be Sept 10-11 at @nygenome.org in NYC! Paper deadline June 1st & in-person registration will open in May. Please sign up for our mailing list groups.google.com/g/mlcb/ for future announcements. More details at mlcb.github.io. Please RP!

14 33

Reposted by Rui Yang

Jacob Schreiber @jmschreiber91.bsky.social · Jan 22

Multiscale footprints reveal the organization of cis-regulatory elements

www.nature.com/articles/s41...

Multiscale footprints reveal the organization of cis-regulatory elements - Nature

We developed PRINT, a computational method that identifies footprints of DNA–protein interactions from bulk and single-cell chromatin accessibility data across multiple scales of protein size.

www.nature.com

14 40

Reposted by Rui Yang

Anshul Kundaje @anshulkundaje.bsky.social · Jan 7

Very excited to announce that the single cell/nuc. RNA/ATAC/multi-ome resource from ENCODE4 is now officially public. This includes raw data, processed data, annotations and pseudobulk products. Covers many human & mouse tissues. 1/

www.encodeproject.org/single-cell/...

Single cell – ENCODEHomo sapiens clickable body map

www.encodeproject.org

6 86 290

Reposted by Rui Yang

Danfeng Chen @danfengc.bsky.social · Jan 6

Happy to share "super admixture", a new framework for modeling the human population structure!
www.biorxiv.org/content/10.1...

Coancestry superposed on admixed populations yields measures of relatedness at individual-level resolution

The admixture model is widely applied to estimate and interpret population structure among individuals. Here we consider a "standard admixture" model that assumes the admixed populations are unrelated...

www.biorxiv.org

1 10 16

Reposted by Rui Yang

Yosef (Yossi) Buganim @yossibuganim.bsky.social · Dec 18

www.nature.com/articles/s41...

(1/n) Ever wonder how transcription factors locate, "invade," and activate their enhancers during cell fate acquisition? 🧬🚀 Check out our latest collaborative work with the Soufi lab, now published in @Nature

Nucleosome fibre topology guides transcription factor binding to enhancers - Nature

Motif grammar on nucleosome fibres acts as signpost elements, directing TF combinatorial binding to enhancers.

www.nature.com

1 15 36

Reposted by Rui Yang

Anshul Kundaje @anshulkundaje.bsky.social · Nov 21

www.nature.com/articles/s41...

Single-molecule states link transcription factor binding to gene expression

Deep insights into multiple facets of TF binding, accessibility & expression with biophysical models of single molecule data by Ben Doughty, Michaela Hinks, Bintu & Greenleaf labs

Single-molecule states link transcription factor binding to gene expression - Nature

A study uses single-molecule footprinting to measure protein occupancy at regulatory elements on individual molecules in human cells and describes how different properties of transcription factor bind...

www.nature.com

12 54

Reposted by Rui Yang

Mitch Guttman @mitchguttman.bsky.social · Nov 27

Gene regulation involves thousands of proteins that bind DNA, yet comprehensively mapping these is challenging. Our paper in Nature Genetics describes ChIP-DIP, a method for genome-wide mapping of hundreds of DNA-protein interactions in a single experiment.
www.nature.com/articles/s41...

ChIP-DIP maps binding of hundreds of proteins to DNA simultaneously and identifies diverse gene regulatory elements - Nature Genetics

ChIP-DIP (ChIP done in parallel) is a highly multiplex assay for protein–DNA binding, scalable to hundreds of proteins including modified histones, chromatin regulators and transcription factors, offe...

www.nature.com

9 150 380

Rui Yang @ruiyang.bsky.social · Nov 26

Highlights:
a) Outperforms supervised models in denoising bulk Hi-C data on new datasets.
b) Denoises Micro-C data at fine resolution (1kb).
c) Reconstructs cell-cluster-specific structures from as few as 50-cell pseudo-bulk at 10kb.
d) Examines single-cell structures at 50kb resolution.

1

Rui Yang @ruiyang.bsky.social · Nov 26

Happy to share HiC2Self, a self-supervised tool for denoising bulk and single-cell Hi-C contact maps!
www.biorxiv.org/content/10.1...

HiC2Self: self-supervised denoising for bulk and single-cell Hi-C contact maps

Hi-C is a chromosome conformation capture assay used to study 3D genome organization. The recent development of single-cell Hi-C technologies has further enabled the examination of 3D chromatin organi...

www.biorxiv.org

1 2 2

Reposted by Rui Yang

Su-In Lee @suinlee.bsky.social · Nov 23

Here is a #compbio starter kit! go.bsky.app/QVPoZXp To all the #Bioinformatics #Genomics #MachineLearning folks: please RP and let’s build this together!

41 45 100

Reposted by Rui Yang

Jacob Schreiber @jmschreiber91.bsky.social · Nov 18

My goal is to understand the regulatory role of every nucleotide in the genome, and how this changes across every cell in the human body.

If you are interested in doing a Ph.D. with me at UMass Chan Medical (Genomics and Comp Bio Department), see the links below. Deadline is Dec 1st.

6 43 120